基于线性回归的飞机战伤抢修时间估算研究  

Study on ABDR Time Assessment Based on Linear Regression

作　　者：刘保军 蔡理[2] 罗湘燕 周平 LIU Baojun;CAI Li;LUO Xiangyan;ZHOU Ping(Aviation Maintenance NCO Academy,Air Force Engineering University,Xinyang 464000,China;Department of Basic Science,Air Force Engineering University,Xi'an 710051,China)

机构地区：[1]空军工程大学航空机务士官学校,河南信阳464000 [2]空军工程大学基础部,西安710051

出　　处：《电光与控制》2020年第2期94-97,共4页Electronics Optics & Control

基　　金：国家自然科学基金(11975311,11405270)

摘　　要：飞机战伤抢修(ABDR)是损伤飞机“再生”的最佳途径,抢修时间估算是评定飞机战伤等级的一个重要依据,也是实施抢修的一个重要前提和条件。针对抢修时间估算涉及的影响因素多的特点,利用主成分分析法进行降维处理,将较多的抢修时间影响因素转换为较少的主成分,并重新解释新的主成分。建立抢修时间估算的多元线性回归模型,且通过遗传算法对回归参数进行优化。实例表明,利用主成分分析法可将12个影响因素降成6个新的主成分,有效减少了回归模型的输入数量,降低了模型的复杂度,且优化的回归模型估算抢修时间的误差较小,平均相对误差为12.82%。Aircraft Battle Damage Repair(ABDR)is the best way for the battle-scarred aircrafts to fly again.The ABDR time assessment is very important for evaluating the battle damage degree of the aircraft and is also a main precondition for making urgent repair.Considering that the ABDR time assessment is influenced by many factors the Principal Components Analysis(PCA)method is used for dimension reduction which transformed the large number of influence factors into uncorrelated new variables known as principal components which are linear combinations of the original variables.The achieved principal components are explained from a new insight.A multiple linear regression model is built for assessing ABDR time.The regressive parameters of the model are optimized through Genetic Algorithm(GA).The following results are obtained by using PCA method:1)The 12 ABDR time assessment influence factors are reduced to 6 new principal components which decreases the input numbers and complexity of the regression model effectively;and 2)The error of ABDR time evaluated by the optimized regression model is smaller with an average relative error of 12.82%.

关 键 词：飞机战伤抢修 抢修时间 线性回归 遗传算法 

分 类 号：E92[军事—军事装备学] TJ07[兵器科学与技术—武器系统与运用工程]